feat: add pre-commit (#4)

* feat: add pre-commit
* fix: auto formatter
* feat: add ci workflow for tests

.github/workflows/changelog.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
 
     permissions:
-      # Give the default GITHUB_TOKEN write permission to commit and push the 
+      # Give the default GITHUB_TOKEN write permission to commit and push the
       # updated CHANGELOG back to the repository.
       # https://github.blog/changelog/2023-02-02-github-actions-updating-the-default-github_token-permissions-to-read-only/
       contents: write

.github/workflows/continuous-integration.yml

@@ -0,0 +1,22 @@
+name: "Continuous Integration"
+
+run-name: Running tests on "${{ github.ref }}" by "${{ github.actor }}"
+
+on:
+  push:
+    # Ignore following branches
+    branches-ignore:
+      - "dev/*"
+
+jobs:
+  # Run pre-commit hooks
+  pre-commit:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+          cache: "pip" # caching pip dependencies
+      - run: pip install -r requirements.txt
+      - run: pre-commit run --all-files

.pre-commit-config.yaml

@@ -0,0 +1,13 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+    -   id: check-yaml
+    -   id: check-added-large-files
+    -   id: check-docstring-first
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace
+-   repo: https://github.com/psf/black
+    rev: 22.10.0
+    hooks:
+    -   id: black

README.md

@@ -2,5 +2,6 @@
 This is a learning repository about DVC Data Version Control and Luigi Pipelines
 
 - luigi, dvc, pre-commit
+- setup https://pre-commit.com/
 - setup https://github.com/Kaggle/kaggle-api
 - `kaggle competitions download -c sentiment-analysis-on-movie-reviews -p data`

requirements.txt

@@ -1,3 +1,4 @@
+pre-commit==3.5.0
 kaggle==1.5.16
 dvc==3.28.0
-luigi==3.4.0
+luigi==3.4.0

source/get_raw_data.py

@@ -2,19 +2,26 @@
 import luigi
 import zipfile
 
+
 class ExtractRawData(luigi.Task):
-    data_path = luigi.Parameter(default="../data/sentiment-analysis-on-movie-reviews.zip")
+    """
+    Extract raw data from zip file
+    """
+
+    data_path = luigi.Parameter(
+        default="../data/sentiment-analysis-on-movie-reviews.zip"
+    )
 
     def output(self):
         return {
-            "test": luigi.LocalTarget('../data/output/test.tsv.zip'),
-            "train": luigi.LocalTarget('../data/output/train.tsv.zip'),
+            "test": luigi.LocalTarget("../data/output/test.tsv.zip"),
+            "train": luigi.LocalTarget("../data/output/train.tsv.zip"),
         }
 
     def run(self):
         # Check if data file exists
         assert os.path.exists(self.data_path)
 
         # Unzip data file
-        with zipfile.ZipFile(self.data_path, 'r') as zip_ref:
+        with zipfile.ZipFile(self.data_path, "r") as zip_ref:
             zip_ref.extractall("../data/output/")